Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3921 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3678. Min Act: -0.0001

Data Index: 664534 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3815. Min Act: -0.0001

Data Index: 1192773 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3572. Min Act: -0.0001

Data Index: 1393096 (Python Code)

Max Activating Token Index: 394

Text #3

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3729. Min Act: -0.0001

Data Index: 795479 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3445. Min Act: -0.0001

Data Index: 1110654 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3416. Min Act: -0.0001

Data Index: 676967 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3273. Min Act: -0.0001

Data Index: 213339 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3351. Min Act: -0.0001

Data Index: 943876 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1251165 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3089. Min Act: -0.0001

Data Index: 1316851 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1176636 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3107. Min Act: -0.0001

Data Index: 646878 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3171. Min Act: -0.0001

Data Index: 463681 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2939. Min Act: -0.0001

Data Index: 1267572 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2857. Min Act: -0.0001

Data Index: 85271 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2879. Min Act: -0.0001

Data Index: 226339 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2852. Min Act: -0.0001

Data Index: 824369 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.3173. Min Act: -0.0001

Data Index: 161216 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2460. Min Act: -0.0001

Data Index: 291134 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.3815. Min Range: -0.3815

Max Act: 0.2525. Min Act: -0.0001

Data Index: 617838 (C4 (Web Text))

Max Activating Token Index: 200